Back to Search
Start Over
Interactive Recommendation with User-Specific Deep Reinforcement Learning.
- Source :
- ACM Transactions on Knowledge Discovery from Data; Oct2019, Vol. 13 Issue 6, p1-15, 15p
- Publication Year :
- 2019
-
Abstract
- In this article, we study a multi-step interactive recommendation problem for explicit-feedback recommender systems. Different from the existing works, we propose a novel user-specific deep reinforcement learning approach to the problem. Specifically, we first formulate the problem of interactive recommendation for each target user as a Markov decision process (MDP). We then derive a multi-MDP reinforcement learning task for all involved users. To model the possible relationships (including similarities and differences) between different users' MDPs, we construct user-specific latent states by using matrix factorization. After that, we propose a user-specific deepQ-learning (UDQN) method to estimate optimal policies based on the constructed user-specific latent states. Furthermore, we propose Biased UDQN (BUDQN) to explicitly model user-specific information by employing an additional bias parameter when estimating the Q-values for different users. Finally, we validate the effectiveness of our approach by comprehensive experimental results and analysis. [ABSTRACT FROM AUTHOR]
Details
- Language :
- English
- ISSN :
- 15564681
- Volume :
- 13
- Issue :
- 6
- Database :
- Complementary Index
- Journal :
- ACM Transactions on Knowledge Discovery from Data
- Publication Type :
- Academic Journal
- Accession number :
- 139359632
- Full Text :
- https://doi.org/10.1145/3359554